Short-Term Projects, Long-Term Benefits: Four Student NLP Projects for Low-Resource Languages
Alexis Palmer, Michaela Regneri · 2014
This paper describes a local effort to bridge the gap between computational and documentary linguistics by teaching stu-dents and young researchers in computa-tional linguistics about doing research and developing systems for low-resource lan-guages. We describe four student software projects developed within one semester. The projects range from a front-end for building small-vocabulary speech recogni-tion systems, to a broad-coverage (more than 1000 languages) language identifi-cation system, to language-specific sys-tems: a lemmatizer for the Mayan lan-guage Uspanteko and named entity recog-nition systems for both Slovak and Per-sian. Teaching efforts such as these are an excellent way to develop not only tools for low-resource languages, but also computa-tional linguists well-equipped to work on endangered and low-resource languages. 1